Explore tools, prompts, skills, news and resources related to Agent 第7页.
Prompt works related to Agent 第7页
Latest articles, prompts, use cases and editorial content about Agent 第7页
NVIDIA announced Jensen Huang's resignation as CEO, president and board member after 33 years, with CFO Colette Kress named interim CEO and a board search underway. The same week saw Google DeepMind launch Gemini 4...
HeMeR is an inference framework for embodied agents that reconciles key-value cache states across declarative, procedural, and working memory as those contents change during interaction. Instead of reprocessing each upda...
The paper presents drydock-eval, a local evaluator for small coding agents that runs jobs in fresh network-isolated containers and checks local scoring behavior against a hosted scorer. It reports throughput of about 250...
This paper introduces ReSHAPE, a task for evaluating whether an agent's revision of a user's initial specification improves planning by better matching acceptable plans. Using ReSHAPE Planter with human-validat...
At the AI Engineer Code Summit, ArtCraft founder Brandon Thomas detailed how the company uses AI agents to recreate popular commercial software as open source, starting with PhotoCraft, a Rust-based Photoshop alternative...
Liquid AI has released LiquidCodec, a ~74M-parameter streaming speech tokenizer that powers its LFM3-Audio-2B and LFM3-Omni-2B models. It converts 24 kHz audio into 12 parallel token streams at 12.5 Hz using grouped fini...
This Microsoft Research podcast roundup highlights several concrete AI advances, including a resolved 31-year-old mathematics challenge known as the KLS conjecture, a new benchmark and method for making AI coding agents...
Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore, to capture lab-operations knowledge and generate diagnostic reports for instrument support tickets. The system uses two runtimes, a 33-skill versioned...
AWS describes how to build a self-service LLM gateway using Amazon Bedrock Application Inference Profiles and LiteLLM running on AWS Fargate, exposing an OpenAI-compatible API for developer tools. The post covers per-use...
AWS published the second part of its Amazon Bedrock cost-governance series, arguing teams should measure cost per task rather than cost per token. It identifies four hidden cost drivers: tokenizer efficiency, output verb...
AWS has released AWS Emulator, a free, CC0-licensed local emulator of AWS APIs that runs on a laptop, dev server or in CI without an AWS account. It covers 200+ services built from 438 Smithy API models, with one Rust cr...
AWS announced updates to the AgentCore runtime, the managed compute layer of Amazon Bedrock AgentCore, which runs each agent session in a hardware-isolated Firecracker MicroVM. The new version scales to 4x more compute (...
AWS ML Blog outlines Agent DLC, a lifecycle for engineering LLM agents from prototype to production around an explicit gold standard of criteria, thresholds and approved examples. It defines six activities—Define, Build,...
AWS describes an architecture for a shared internal AI assistant that scopes knowledge base searches to each authenticated user. The pattern combines Amazon Bedrock Managed Knowledge Base ACL awareness, MCP tools exposed...
AWS published a reference architecture for composing multi-agent systems across organizational boundaries using the Agent-to-Agent (A2A) protocol. The demo runs a LangChain-based enterprise orchestrator and a Strands Age...
ElevenLabs has released Scribe v3 and Scribe v3 Live, speech recognition models designed to transcribe accurately amid background noise and crosstalk. Artificial Analysis benchmarks show Scribe v3 narrowly beating OpenAI...
Google DeepMind has unveiled AlphaGenome 2, a genomics AI model that analyzes genetic variants at individual cell-type resolution rather than across bulk tissue. It was trained on more than 107 million cell profiles and...
Google introduced Gemini Decision 1, a calibrated multimodal decision model for closed-set classification tasks, supporting up to 1,000 questions per request with 256K context and ~200ms end-to-end latency. Priced at $0....